GPU-48xCPU-480GB-2xB200 by UpCloud
(All-cores)
(Single-core)
Specifications #
Server Metadata #
Vendor ID | upcloud |
Name | GPU-48xCPU-480GB-2xB200 |
Description | GPU (48 vCPUs, 480 GiB RAM, 2x B200) |
Family | GPU |
Series | B200 |
Hw Virt | |
Average Time To Start | 84 |
Status | inactive |
Observed At | 2026-11-17T04:26:57.347792 |
Availability #
| Region / ID | Spot | Ondemand |
|---|---|---|
Sydney #1 (AU) / au-syd1 | 7.4345 USD/h | 9.9126 USD/h |
Frankfurt #1 (DE) / de-fra1 | 7.4345 USD/h | 9.9126 USD/h |
Copenhagen #1 (DK) / dk-cph1 | 7.4345 USD/h | 9.9126 USD/h |
Madrid #1 (ES) / es-mad1 | 7.4345 USD/h | 9.9126 USD/h |
Helsinki #1 (FI) / fi-hel1 | 7.4345 USD/h | 9.9126 USD/h |
Amsterdam #1 (NL) / nl-ams1 | 7.4345 USD/h | 9.9126 USD/h |
Stavanger #1 (NO) / no-svg1 | 7.4345 USD/h | 9.9126 USD/h |
Warsaw #1 (PL) / pl-waw1 | 7.4345 USD/h | 9.9126 USD/h |
Stockholm #1 (SE) / se-sto1 | 7.4345 USD/h | 9.9126 USD/h |
Singapore #1 (SG) / sg-sin1 | 7.4345 USD/h | 9.9126 USD/h |
London #1 (GB) / uk-lon1 | 7.4345 USD/h | 9.9126 USD/h |
Chicago #1 (US) / us-chi1 | 7.4345 USD/h | 9.9126 USD/h |
New York #1 (US) / us-nyc1 | 7.4345 USD/h | 9.9126 USD/h |
San Jose #1 (US) / us-sjo1 | 7.4345 USD/h | 9.9126 USD/h |
Helsinki #2 (FI) / fi-hel2 | 8.1063 USD/h | 11.5867 USD/h |
Processor #
vCPUs | 48 |
Hypervisor | KVM |
CPU Allocation | Shared |
CPU Cores | 48 |
CPU Speed | 2 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
CPU Family | Xeon |
CPU Model | 8570 |
CPU L1D Cache | 32 KiB |
CPU L1D Cache Total | 2 MiB |
CPU L1I Cache | 32 KiB |
CPU L1I Cache Total | 2 MiB |
CPU L2 Cache | 4 MiB |
CPU L2 Cache Total | 192 MiB |
CPU L3 Cache | 16 MiB |
CPU L3 Cache Total | 16 MiB |
CPU Flags | fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, arch_perfmon, rep_good, nopl, xtopology, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pdcm, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, bus_lock_detect, cldemote, movdiri, movdir64b, fsrm, md_clear, serialize, tsxldtrk, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities |
Ecpus | 44.8 |
Scalability | 93.33 |
System Resources and Accelerators #
| Memory | |
|---|---|
Memory Amount | 480 GiB |
Memory Amount Actual | 480 GiB |
| Accelerators | |
|---|---|
Accelerator Count | 2 |
Accelerator Memory Min | 192 GiB |
Accelerator Memory Total | 384 GiB |
Accelerator Type | GPU |
Accelerator Manufacturer | NVIDIA |
Accelerator Family | Blackwell |
Accelerator Model | B200 |
Accelerators |
|
| Storage | |
|---|---|
Storage Size | 0 GB |
Storages | |
Compatible Storage IDs | maxiops, standard, hdd |
| Network | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 71680 GB/month |
IPv4 | 1 |
CPU and System Topology #
Server Description #
High-density GPU acceleration with dual Blackwell GPUs and massive memory for advanced AI inference and parallel computing workloads.
UpCloud GPU-48xCPU-480GB-2xB200 is a high-performance GPU-accelerated server built on the x86_64 architecture, featuring an Intel Xeon 8570 processor with 48 physical cores and 48 vCPUs. It is equipped with 480.0 GB of system memory and two NVIDIA Blackwell B200 GPUs delivering 384 GB of VRAM, though it includes no local storage. Benchmarks show top-tier performance in Passmark CPU tests, multi-threaded decompression, and large-block memory read bandwidth, alongside strong multi-core processing. This instance is optimized for demanding workloads such as large language model inference, deep learning, and high-throughput database operations.
Economics #
Performance #
GPU Bandwidth and Latency #
| Node (all GPUs) | |
|---|---|
Node baseline directional bandwidth | 95.4 GB/s |
Node GPU-to-host bandwidth | 111.5 GB/s |
Node host-to-GPU bandwidth | 111.3 GB/s |
| Peer-to-peer | |
|---|---|
GPU-to-GPU P2P duplex bandwidth | 770.4 GB/s |
GPU-to-GPU P2P gather bandwidth | 774.3 GB/s |
GPU-to-GPU P2P latency | 1,616 ns |
GPU-to-GPU P2P bandwidth | 774.7 GB/s |
| Single GPU slot | |
|---|---|
Per-GPU GPU-to-host bandwidth | 56.1 GB/s |
Per-GPU host-to-GPU bandwidth | 55.7 GB/s |
Per-GPU host-device latency | 989 ns |
Per-GPU device memory copy bandwidth | 3193.9 GB/s |
| Benchmark Environment | |
|---|---|
Driver Version | 595.71.05 |
CUDA Version (driver) | 13.2 |
nvbandwidth Version | v0.8 |
GPU Count | 2 |
P2P Supported | Yes |
| Efficiency | |
|---|---|
SM/CE copy efficiency | 0.92 |
Memory Bandwidth#
Compression #
OpenSSL #
Geekbench Single-Core #
Geekbench Multi-Core #
Passmark CPU Scores #
| BENCHMARK | SCORE |
|---|---|
Mark | 88,534 |
Compression | 1,247,655 |
Encryption | 71,927 |
Extended Instructions | 132,359 |
Floating Point Maths | 338,097 |
Integer Maths | 288,059 |
Physics | 16,556 |
Prime Numbers | 905 |
Single Threaded | 3,236 |
String Sorting | 173,130 |
Passmark Memory Scores #
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2,401 |
Database Operations | 33,289 |
Memory Latency | 61 |
Memory Read Cached | 29,115 |
Memory Read Uncached | 8,040 |
Memory Write | 7,846 |
Stress-ng Stressors #
| CPU integer | Single | Multi | Scaling |
|---|---|---|---|
atomic | 198.47 | 223.24 | 1.12× |
bitops | 166,166 | 6,872,998 | 41.36× |
branch | 156,700 | 6,466,545 | 41.27× |
funccall | 848.41 | 35,608 | 41.97× |
funcret | 13,949 | 589,517 | 42.26× |
hash | 199,201 | 8,363,828 | 41.99× |
intmath | 71,549 | 2,966,334 | 41.46× |
nop | 294,595 | 14,052,571 | 47.70× |
prime | 525,602 | 24,604,120 | 46.81× |
rotate | 111,470 | 5,274,172 | 47.31× |
str | 1,049,103 | 49,429,591 | 47.12× |
wcs | 771,016 | 35,269,326 | 45.74× |
| Cryptography | Single | Multi | Scaling |
|---|---|---|---|
crypt | 3,802 | 151,834 | 39.93× |
| Compression | Single | Multi | Scaling |
|---|---|---|---|
jpeg | 917.36 | 38,905 | 42.41× |
zlib | 63.37 | 2,696 | 42.55× |
| Hypervisor | Single | Multi | Scaling |
|---|---|---|---|
clock | 45,498 | 188,182 | 4.14× |
clone | 385.71 | 13,389 | 34.71× |
context | 5,091 | 211,635 | 41.57× |
cpu-sched | 73.57 | 3,096 | 42.08× |
eventfd | 73,886 | 1,263,164 | 17.10× |
fault | 31,166 | 140,331 | 4.50× |
fork | 2,602 | 70,280 | 27.01× |
getrandom | 67,438 | 2,833,717 | 42.02× |
hrtimers | 520,126 | 3,063,119 | 5.89× |
mprotect | 595,537 | 15,425,469 | 25.90× |
mtx | 26,548,230 | 3,322,978,171 | 125.17× |
munmap | 1,919 | 60,525 | 31.53× |
null | 801,761 | 32,759,584 | 40.86× |
pipe | 727,909 | 23,022,719 | 31.63× |
priv-instr | 827,268 | 8,965,365 | 10.84× |
resched | 10,107,815 | 14,094,337 | 1.39× |
switch | 118,879 | 15,793,689 | 132.85× |
timermix | 263,279 | 11,953,500 | 45.40× |
tlb-shootdown | 9,451 | 175,286 | 18.55× |
tsc | 649,266 | 30,887,671 | 47.57× |
usersyscall | 715,085 | 8,614,207 | 12.05× |
vdso | 88,500,336 | 4,214,735,748 | 47.62× |
vfork | 22,114 | 159,544 | 7.21× |
x86syscall | 8,898,090 | 361,024,546 | 40.57× |
yield | 52,783,454 | 70,267,909 | 1.33× |
zero | 4,952,575 | 203,710,306 | 41.13× |
| CPU float/SIMD | Single | Multi | Scaling |
|---|---|---|---|
eigen | 17,882 | 749,732 | 41.93× |
expmath | 3,949 | 165,212 | 41.84× |
fma | 1,466,294 | 61,301,196 | 41.81× |
fp | 224.38 | 9,482 | 42.26× |
fractal | 7.2 | 303.69 | 42.18× |
hyperbolic | 4,553 | 192,092 | 42.19× |
logmath | 5,824 | 248,311 | 42.64× |
matrix | 5,344 | 241,973 | 45.28× |
matrix-3d | 788.97 | 19,661 | 24.92× |
monte-carlo | 290.33 | 13,868 | 47.77× |
mpfr | 1,967 | 92,824 | 47.20× |
powmath | 2,200 | 105,196 | 47.81× |
trig | 3,003 | 142,417 | 47.43× |
veccmp | 28,096 | 1,314,365 | 46.78× |
vecfp | 1,733 | 82,297 | 47.49× |
vecmath | 4,404 | 179,310 | 40.72× |
vecshuf | 926.16 | 44,125 | 47.64× |
vecwide | 40,190 | 1,909,975 | 47.52× |
| Algorithms | Single | Multi | Scaling |
|---|---|---|---|
bitonicsort | 10 | 406.99 | 40.70× |
bsearch | 322.93 | 13,321 | 41.25× |
bubblesort | 1.2 | 48 | 40.00× |
fibsearch | 342.66 | 14,478 | 42.25× |
heapsort | 11.2 | 469.99 | 41.96× |
hsearch | 9,443 | 395,340 | 41.87× |
insertionsort | 14.4 | 595.8 | 41.37× |
malloc | 2,993,921 | 55,101,032 | 18.40× |
mcontend | 57.1 | 7,432 | 130.16× |
mergesort | 34.4 | 1,626 | 47.26× |
qsort | 24.6 | 1,145 | 46.56× |
skiplist | 6,105 | 290,064 | 47.52× |
tree | 1.8 | 86.25 | 47.92× |
| Memory | Single | Multi | Scaling |
|---|---|---|---|
cache | 686,461 | 1,275,616 | 1.86× |
cachehammer | 196,011 | 7,309,693 | 37.29× |
cacheline | 33.38 | 3,157 | 94.58× |
l1cache | 362.89 | 15,004 | 41.35× |
memcpy | 497.16 | 20,933 | 42.11× |
memrate | 0.12 | 5.35 | 44.58× |
memthrash | 212.57 | 1,761 | 8.28× |
ptr-chase | 29,914,321 | 843,093,625 | 28.18× |
spinmem | 228.18 | 2,577 | 11.29× |
stream | 122.74 | 108,949 | 887.64× |
vm | 199,252 | 297,915 | 1.50× |
Stress-ng Raw Scores #
Stress-ng Relative Multicore Performance #
Static Web Server#
Redis#
Alternatives #
Servers of the Same Family #
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| GPU-8xCPU-64GB-1xL40S | 8 | 64 GiB | 1 |
| GPU-12xCPU-128GB-1xL40S | 12 | 128 GiB | 1 |
| GPU-12xCPU-240GB-1xH100 | 12 | 240 GiB | 1 |
| GPU-12xCPU-128GB-2xL40S | 12 | 128 GiB | 2 |
| GPU-16xCPU-80GB-1xRTXPRO6000 | 16 | 80 GiB | 1 |
| GPU-16xCPU-192GB-1xL40S | 16 | 192 GiB | 1 |
| GPU-16xCPU-192GB-2xL40S | 16 | 192 GiB | 2 |
Similar Servers #
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|